Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 386 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3731. Min Act: -0.0001

Data Index: 1300797 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3633. Min Act: -0.0001

Data Index: 276320 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3633. Min Act: -0.0001

Data Index: 48390 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3483. Min Act: -0.0001

Data Index: 818846 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3390. Min Act: -0.0001

Data Index: 991349 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3267. Min Act: -0.0001

Data Index: 1177157 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3252. Min Act: -0.0001

Data Index: 1034586 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3024. Min Act: -0.0001

Data Index: 751980 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3601. Min Act: -0.0001

Data Index: 61872 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3337. Min Act: -0.0001

Data Index: 608841 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3337. Min Act: -0.0001

Data Index: 973830 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3322. Min Act: -0.0001

Data Index: 773429 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3534. Min Act: -0.0001

Data Index: 14336 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3377. Min Act: -0.0001

Data Index: 1127854 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3381. Min Act: -0.0001

Data Index: 1160835 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3155. Min Act: -0.0001

Data Index: 656607 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3272. Min Act: -0.0001

Data Index: 812055 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3266. Min Act: -0.0001

Data Index: 998296 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3036. Min Act: -0.0001

Data Index: 514527 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.3731. Min Range: -0.3731

Max Act: 0.3132. Min Act: -0.0001

Data Index: 527547 (C4 (Web Text))

Max Activating Token Index: 542